Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model
- 28 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10099-10113
Abstract
Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://github.com/lauht/PA-TMM.Keywords
Funding Information
- National Natural Science Foundation of China (62272373)
This publication has 54 references indexed in Scilit:
- Exploring Multi-Time Context Vector and Randomness for Stock Movement Prediction2022
- Multi-source aggregated classification for stock price movement predictionInformation Fusion, 2022
- Stock Price Prediction Under Anomalous Circumstances2020
- Hardening Soft Information: A Transformer-Based Approach to Forecasting Stock Return Volatility2020
- Predicting Stock Price Movements with Text Data using Labeling based on Financial Theory2020
- Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting2020
- Shared analyst coverage: Unifying momentum spillover effectsJournal of Financial Economics, 2020
- Industry Information Diffusion and the Lead-lag Effect in Stock ReturnsThe Review of Financial Studies, 2007
- Toward a positive theory of consumer choiceJournal of Economic Behavior & Organization, 1980
- Comparison of the predicted and observed secondary structure of T4 phage lysozymeBiochimica et Biophysica Acta (BBA) - Protein Structure, 1975